© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217491
    Prev
    Next
    INDEX
    Explanations

    cocktails drinks

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Y
    0.83
    Y
    0.66
    Ｙ
    0.64
     y
    0.58
     ય
    0.51
     ইয়
    0.49
    Ys
    0.49
     य
    0.48
     getY
    0.46
    ACH
    0.44
    POSITIVE LOGITS
     Fle
    0.42
     Bec
    0.42
    льны
    0.41
     خاک
    0.39
     Bel
    0.39
     разъ
    0.38
    Vil
    0.38
     Віль
    0.38
    лери
    0.38
    踱
    0.37
    Activations Density 0.002%

    No Known Activations